Embodiments of the present disclosure relate to generating velocity profiles for an autonomous vehicle (101). An ECU (107) of the autonomous vehicle (101) receives road information from one or more sensors (106) associated with the autonomous vehicle (101). One or more parameters related to smooth movement of the autonomous vehicle on the road is determined from the road information. Further, a first velocity profile is produced using an AI model and a second velocity profile is produced using a hierarchical model, based on the one or more parameters. Furthermore, one of the first and the second velocity profile is selected by comparing the first and the second velocity profiles. The selected velocity profile has a lower value of velocity value compared to the other velocity profile. The selected velocity profile is provided to the autonomous vehicle (101) for navigating on the road (102) smoothly.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The method of claim 1, wherein the road information comprises at least one of, a speed breaker, an inclination, a turn, a pothole, a road boundary, an obstacle, a traffic sign, a road sign, and a median.
3. The method of claim 1, wherein the AI model is trained to indicate the most relevant velocity profile from a plurality of velocity profiles using the one or more road parameters provided as input.
5. The method of claim 1, wherein comparing comprises selecting a lesser velocity value among the first velocity profile and the second velocity profile when a difference is above a threshold value.
6. The method of claim 5, wherein the one or more road parameters and the selected velocity profile from the first velocity profile are fed back to enhance the AI model upon the difference between the first velocity profile and the second velocity profile is above the threshold value, wherein the AI model updates one or more model parameters based on the feedback.
7. The non-transitory computer readable medium of claim 1, wherein the AI model is trained to indicate the most relevant velocity profile from a plurality of velocity profiles using the one or more road parameters provided as input.
9. The ECU of claim 8, wherein the processor trains the AI model to indicate the most relevant velocity profile from a plurality of velocity profiles using the one or more road parameters provided as input.
11. The ECU of claim 8, wherein the processor compares by selecting a lesser velocity value among the first velocity profile and the second velocity profile when a difference is above a threshold value.
12. The ECU of claim 11, wherein the processor feedback the one or more road parameters and the selected velocity profile from the first velocity profile to enhance the AI model upon the difference between the first velocity profile and the second velocity profile is above the threshold value, wherein the AI model updates one or more model parameters based on the feedback.
14. The non-transitory computer readable medium of claim 13, wherein the road information comprises at least one of, a speed breaker, an inclination, a turn, a pothole, a road boundary, an obstacle, a traffic sign, a road sign, and a median.
16. The non-transitory computer readable medium of claim 13, wherein comparing comprises selecting a lesser velocity value among the first velocity profile and the second velocity profile when a difference is above a threshold value, wherein the one or more road parameters and the selected velocity profile from the first velocity profile are fed back to enhance the AI model upon the difference between the first velocity profile and the second velocity profile is above the threshold value, wherein the AI model updates one or more model parameters based on the feedback.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 30, 2020
December 6, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.